© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18247
    Prev
    Next
    INDEX
    Explanations

    screen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     энд
    -0.08
    ifye
    -0.08
     involve
    -0.07
    culated
    -0.07
     include
    -0.07
    	Input
    -0.07
    Backup
    -0.07
    -backed
    -0.07
     {:?}",
    -0.07
    anks
    -0.07
    POSITIVE LOGITS
     toont
    0.11
     mostrando
    0.10
     montr
    0.10
     showcasing
    0.10
     показывает
    0.10
    展示
    0.09
     menunjukkan
    0.09
     naast
    0.09
     showing
    0.09
    显示
    0.09
    Activations Density 0.003%

    No Known Activations